The association between PM2.5 components and blood pressure changes in late pregnancy: A combined analysis of traditional and machine learning models

Lijie Wang; Li Wen; Jianling Shen; Yi Wang; Qiannan Wei; Wenjie He; Xueting Liu; Peiyao Chen; Yan Jin; Dingli Yue; Yuhong Zhai; Huiying Mai; Xiaoling Zeng; Qiansheng Hu; Weiwei Lin

doi:10.1016/j.envres.2024.118827

The association between PM_2.5 components and blood pressure changes in late pregnancy: A combined analysis of traditional and machine learning models

Environ Res. 2024 Apr 3;252(Pt 1):118827. doi: 10.1016/j.envres.2024.118827. Online ahead of print.

Authors

Lijie Wang¹, Li Wen¹, Jianling Shen¹, Yi Wang¹, Qiannan Wei¹, Wenjie He¹, Xueting Liu¹, Peiyao Chen¹, Yan Jin¹, Dingli Yue², Yuhong Zhai², Huiying Mai³, Xiaoling Zeng³, Qiansheng Hu⁴, Weiwei Lin⁵

Affiliations

¹ Department of Occupational and Environmental Health, School of Public Health, Sun Yat-Sen University, Guangzhou, 510080, China.
² Guangdong Ecological and Environmental Monitoring Center, State Environmental Protection Key Laboratory of Regional Air Quality Monitoring, Guangzhou, 510308, China.
³ Department of Obstetrics and Gynecology, Heshan Maternal and Child Health Hospital, Jiangmen, 529700, China.
⁴ Department of Occupational and Environmental Health, School of Public Health, Sun Yat-Sen University, Guangzhou, 510080, China. Electronic address: huqsh@mail.sysu.edu.cn.
⁵ Department of Occupational and Environmental Health, School of Public Health, Sun Yat-Sen University, Guangzhou, 510080, China. Electronic address: linweiw5@mail.sysu.edu.cn.

PMID: 38580006
DOI: 10.1016/j.envres.2024.118827

Abstract

Background: PM_2.5 is a harmful mixture of various chemical components that pose a challenge in determining their individual and combined health effects due to multicollinearity issues with traditional linear regression models. This study aimed to develop an analytical methodology combining traditional and novel machine learning models to evaluate PM_2.5's combined effects on blood pressure (BP) and identify the most toxic components.

Methods: We measured late-pregnancy BP of 1138 women from the Heshan cohort while simultaneously analyzing 31 PM_2.5 components. We utilized multiple linear regression modeling to establish the relationship between PM_2.5 components and late-pregnancy BP and applied Random Forest (RF) and generalized Weighted Quantile Sum (gWQS) regression to identify the most toxic components contributing to elevated BP and to quantitatively evaluate the cumulative effect of the PM_2.5 component mixtures.

Results: The results revealed that 16 PM_2.5 components, such as EC, OC, Ti, Fe, Mn, Cu, Cd, Mg, K, Pb, Se, Na⁺, K⁺, Cl^-, NO₃^-, and F^-, contributed to elevated systolic blood pressure (SBP), while 26 components, including two carbon components (EC, OC), fourteen metallics (Ti, Fe, Mn, Cr, Mo, Co, Cu, Zn, Cd, Na, Mg, Al, K, Pb), one metalloid (Se), and nine water-soluble ions (Na⁺, K⁺, Mg²⁺, Ca²⁺, NH₄⁺, Cl^-, NO₃^-, SO₄^2-, F^-), contributed to elevated diastolic blood pressure (DBP). Mn and Cr were the most toxic components for elevated SBP and DBP, respectively, as analyzed by RF and gWQS models and verified against each other. Exposure to PM_2.5 component mixtures increased SBP by 1.04 mmHg (95% CI: 0.33-1.76) and DBP by 1.13 mmHg (95% CI: 0.47-1.78).

Conclusions: Our study highlights the effectiveness of combining traditional and novel models as an analytical strategy to quantify the health effects of PM_2.5 constituent mixtures.

Keywords: Blood pressure; Chemical components; Machine learning; PM(2.5); Pregnant women.